def transformer_models(model_name):
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
qa_pipeline = pipeline('question-answering',
model=model,
tokenizer=tokenizer)
return qa_pipeline
def __init__(self, CONFIG):
super().__init__()
self.CONFIG = CONFIG
self.modelpath = "ahotrod/roberta_large_squad2"
self.robertaconfig = AutoConfig.from_pretrained(self.modelpath)
self.robertaconfig.output_hidden_states = True
self.roberta = AutoModelForQuestionAnswering.from_pretrained(
self.modelpath,
config=self.robertaconfig,
)._modules['roberta']
self.drop_out = nn.Dropout(p=self.CONFIG['DROPOUT'])
self.high_dropout = nn.Dropout(p=self.CONFIG['HIGH_DROPOUT'])
n_weights = self.robertaconfig.num_hidden_layers + 1
weights_init = torch.zeros(n_weights).float()
weights_init.data[:self.CONFIG['MAIN_LAYERS']] = -3
self.layer_weights = torch.nn.Parameter(weights_init)
if self.CONFIG['QA_TASK']:
if not self.CONFIG['ADD_TOKEN_LOSS']:
self.classifier = nn.Linear(self.robertaconfig.hidden_size, 2)
else:
self.classifier = nn.Linear(self.robertaconfig.hidden_size, 3)
def __init__(self, CONFIG):
super().__init__()
self.CONFIG = CONFIG
self.modelpath = "ahotrod/roberta_large_squad2"
self.robertaconfig = AutoConfig.from_pretrained(self.modelpath)
self.robertaconfig.output_hidden_states = True
self.roberta = AutoModelForQuestionAnswering.from_pretrained(
self.modelpath,
config=self.robertaconfig,
)._modules['roberta']
self.dropout = nn.Dropout(p=self.CONFIG['DROPOUT'])
self.l1 = AutoModelForQuestionAnswering.from_pretrained(
self.modelpath,
config=self.robertaconfig,
)._modules['qa_outputs']
def __init__(self):
model = AutoModelForQuestionAnswering.from_pretrained("/model/model")
tokenizer = AutoTokenizer.from_pretrained("/model/tokenizer")
self.default_response = "Perhaps the answer is 42."
self.predictor = pipeline("question-answering",
model=model,
tokenizer=tokenizer)
with open("/mounts/bert_context/paragraph.txt") as f:
self.context = f.read()
def test_conversion_adaptive_model_qa():
farm_model = Converter.convert_from_transformers(
"deepset/bert-base-cased-squad2", device="cpu")
transformer_model = farm_model.convert_to_transformers()[0]
transformer_model2 = AutoModelForQuestionAnswering.from_pretrained(
"deepset/bert-base-cased-squad2")
# compare weights
for p1, p2 in zip(transformer_model.parameters(),
transformer_model2.parameters()):
assert (p1.data.ne(p2.data).sum() == 0)
def test_conversion_adaptive_model(caplog):
if caplog:
caplog.set_level(logging.CRITICAL)
model = AdaptiveModel.convert_from_transformers(
"deepset/bert-base-cased-squad2",
device="cpu",
task_type="question_answering")
transformer_model = model.convert_to_transformers()
transformer_model2 = AutoModelForQuestionAnswering.from_pretrained(
"deepset/bert-base-cased-squad2")
# compare weights
for p1, p2 in zip(transformer_model.parameters(),
transformer_model2.parameters()):
assert (p1.data.ne(p2.data).sum() == 0)
import argparse
import os
import shutil
from transformers.modeling_auto import AutoModelForQuestionAnswering
from transformers.tokenization_auto import AutoTokenizer
parser = argparse.ArgumentParser()
parser.add_argument("--model")
args = parser.parse_args()
model = AutoModelForQuestionAnswering.from_pretrained(args.model)
tokenizer = AutoTokenizer.from_pretrained(args.model)
os.makedirs("model")
os.makedirs("tokenizer")
model.save_pretrained("model")
tokenizer.save_pretrained("tokenizer")
shutil.copyfile("model/config.json", "tokenizer/config.json")
import time
import torch
import Bert_Embeddings as be
from transformers import pipeline
from flask import Flask, redirect, url_for, request, render_template, jsonify
from transformers.modeling_auto import AutoModelForQuestionAnswering
from transformers.tokenization_auto import AutoTokenizer
app = Flask(__name__)
tokenizer = AutoTokenizer.from_pretrained(
"bert-large-uncased-whole-word-masking-finetuned-squad")
model = AutoModelForQuestionAnswering.from_pretrained(
"bert-large-uncased-whole-word-masking-finetuned-squad")
qa_pipeline = pipeline(
"question-answering",
model="bert-large-uncased-whole-word-masking-finetuned-squad",
tokenizer="bert-large-uncased-whole-word-masking-finetuned-squad")
path = 'source_sample_tesla.txt'
corpus_embeddings, embedder, corpus, sentences, para = be.load_model(path)
def sim_sent(query):
start = time.time()
queries = [query]
results = be.ComputeSim(corpus_embeddings, embedder, queries)
text = []
for idx in results:
text.append(corpus[idx])